Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 7526
    Prev
    Next
    INDEX
    Explanations

    mentions of added features or improvements in a product or system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the introduction and enhancement of features or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Telephone
    -0.56
     Rasmussen
    -0.56
     Lincoln
    -0.52
    odore
    -0.51
     ALP
    -0.51
    thur
    -0.50
     Omaha
    -0.50
    icz
    -0.50
     Mandela
    -0.49
     Marathon
    -0.49
    POSITIVE LOGITS
     abound
    0.75
     respectively
    0.70
     throughout
    0.69
     besides
    0.65
     populate
    0.63
     plent
    0.63
     synerg
    0.62
     redund
    0.62
    cellaneous
    0.60
     interchange
    0.60
    Activations Density 0.709%

    No Known Activations